Skip to content

Instantly share code, notes, and snippets.

View BasedLukas's full-sized avatar
🚀
e/acc

BasedLukas

🚀
e/acc
View GitHub Profile
@BasedLukas
BasedLukas / double_q.py
Created March 16, 2024 18:34
Comparison of Q-learning with Double Q-learning
import numpy as np
import random
import matplotlib.pyplot as plt
from typing import Dict, Optional, Tuple
def argmax_a(state: str, q: Dict) -> int:
"""
Find the action that maximizes the Q-value in a given state.